Enabling Depth-driven Visual Attention on the iCub Humanoid Robot: Instructions for Use and New Perspectives

TL;DR

This paper demonstrates that using the ELAS stereo matching algorithm enables real-time depth perception on the iCub robot, facilitating natural and effective attention-based behaviors through disparity-driven segmentation.

Contribution

It shows that ELAS is suitable for humanoid robots and illustrates how reliable stereo depth can simplify complex visual attention tasks in real-world settings.

Findings

ELAS provides fast, robust disparity maps on iCub.

Disparity-based segmentation effectively guides robot attention.

Depth cues simplify visual behavior implementation.

Abstract

The importance of depth perception in the interactions that humans have within their nearby space is a well established fact. Consequently, it is also well known that the possibility of exploiting good stereo information would ease and, in many cases, enable, a large variety of attentional and interactive behaviors on humanoid robotic platforms. However, the difficulty of computing real-time and robust binocular disparity maps from moving stereo cameras often prevents from relying on this kind of cue to visually guide robots' attention and actions in real-world scenarios. The contribution of this paper is two-fold: first, we show that the Efficient Large-scale Stereo Matching algorithm (ELAS) by A. Geiger et al. 2010 for computation of the disparity map is well suited to be used on a humanoid robotic platform as the iCub robot; second, we show how, provided with a fast and reliable stereo system, implementing relatively challenging visual behaviors in natural settings can require much less effort. As a case of study we consider the common situation where the robot is asked to focus the attention on one object close in the scene, showing how a simple but effective disparity-based segmentation solves the problem in this case. Indeed this example paves the way to a variety of other similar applications.